3-D Shape Estimation and Image Restoration

Images contain information about the spatial properties of the scene they depict. When coupled with suitable assumptions, images can be used to infer three-dimensional information. This useful volume concentrates on motion blur and defocus, which can be exploited to infer the 3-D structure of a scene as well as its radiance properties and which in turn can be used to generate novel images with better quality. The book presents a coherent analytical framework for the analysis and design of algorithms to estimate 3-D shape from defocused and motion blurred images, and to eliminate defocus and motion blur to yield "restored" images. It further provides a collection of algorithms that are optimal with respect to the chosen model and estimation criterion.

Images contain information about the spatial properties of the scene they depict. When coupled with suitable assumptions, images can be used to infer thr- dimensional information. For instance, if the scene contains objects made with homogeneous material, such as marble, variations in image intensity can be - sociated with variations in shape, and hence the "shading" in the image can be exploited to infer the "shape" of the scene (shape from shading). Similarly, if the scene contains (statistically) regular structures, variations in image intensity can be used to infer shape (shape from textures). Shading, texture, cast shadows, - cluding boundaries are all "cues" that can be exploited to infer spatial properties of the scene from a single image, when the underlying assumptions are sat- ?ed. In addition, one can obtain spatial cues from multiple images of the same scene taken with changing conditions. For instance, changes in the image due to a moving light source are used in "photometric stereo," changes in the image due to changes in the position of the cameras are used in "stereo," "structure from motion," and "motion blur. " Finally, changes in the image due to changes in the geometry of the camera are used in "shape from defocus. " In this book, we will concentrate on the latter two approaches, motion blur and defocus, which are referred to collectively as "accommodation cues.

In the areas of image processing and computer vision, there is a particular need for software that can infer the three-dimensional shape of a scene. This book describes the analytical processes that go into designing such software. It also presents original algorithms.

Images contain information about the spatial properties of the scene they depict. When coupled with suitable assumptions, images can be used to infer three-dimensional information. This useful volume concentrates on motion blur and defocus, which can be exploited to infer the 3-D structure of a scene - as well as its radiance properties - and which in turn can be used to generate novel images with better quality. The book presents a coherent analytical framework for the analysis and design of algorithms to estimate 3-D shape from defocused and motion blurred images, and to eliminate defocus and motion blur to yield "restored" images. It further provides a collection of algorithms that are optimal with respect to the chosen model and estimation criterion.

Basic models of image formation.- Some analysis: When can 3-D shape be reconstructed from blurred images?.- Least-squares shape from defocus.- Enforcing positivity: Shape from defocus and image restoration by minimizing I-divergence.- Defocus via diffusion: Modeling and reconstruction.- Dealing with motion: Unifying defocus and motion blur.- Dealing with multiple moving objects.- Dealing with occlusions.- Final remarks.